{"id":"https://openalex.org/W2919487069","doi":"https://doi.org/10.21428/5b03f636","title":"Batch Reinforcement Learning on a RoboCup SSL Keepaway Strategy Learning Problem","display_name":"Batch Reinforcement Learning on a RoboCup SSL Keepaway Strategy Learning Problem","publication_year":2019,"publication_date":"2019-03-05","ids":{"openalex":"https://openalex.org/W2919487069","doi":"https://doi.org/10.21428/5b03f636","mag":"2919487069"},"language":"en","primary_location":{"id":"doi:10.21428/5b03f636","is_oa":true,"landing_page_url":"https://doi.org/10.21428/5b03f636","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"CRoNe2018: 4th Congress on Robotics and Neuroscience","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.21428/5b03f636","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018440712","display_name":"Franco Ollino","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Franco Ollino","raw_affiliation_strings":["Universidad T\u00e9cnica"],"affiliations":[{"raw_affiliation_string":"Universidad T\u00e9cnica","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019734269","display_name":"Miguel A. Sol\u00eds","orcid":"https://orcid.org/0000-0002-5735-8834"},"institutions":[{"id":"https://openalex.org/I2802166871","display_name":"Universidad Cat\u00f3lica del Norte","ror":"https://ror.org/02akpm128","country_code":"CL","type":"education","lineage":["https://openalex.org/I2802166871"]}],"countries":["CL"],"is_corresponding":true,"raw_author_name":"Miguel A. Sol\u00eds","raw_affiliation_strings":["Universidad Cat\u00f3lica del Norte;","Centro de Innovaci\u00f3n y Rob\u00f3tica"],"affiliations":[{"raw_affiliation_string":"Universidad Cat\u00f3lica del Norte;","institution_ids":["https://openalex.org/I2802166871"]},{"raw_affiliation_string":"Centro de Innovaci\u00f3n y Rob\u00f3tica","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030111247","display_name":"H\u00e9ctor Allende","orcid":"https://orcid.org/0000-0002-9899-0051"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"H\u00e9ctor Allende","raw_affiliation_strings":["Universidad T\u00e9cnica"],"affiliations":[{"raw_affiliation_string":"Universidad T\u00e9cnica","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5019734269"],"corresponding_institution_ids":["https://openalex.org/I2802166871"],"apc_list":null,"apc_paid":null,"fwci":0.2175,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.58442975,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9715999960899353,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9715999960899353,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.9642999768257141,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.942799985408783,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7835937738418579},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6135517954826355},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5816173553466797},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35012662410736084}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7835937738418579},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6135517954826355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5816173553466797},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35012662410736084}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21428/5b03f636","is_oa":true,"landing_page_url":"https://doi.org/10.21428/5b03f636","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"CRoNe2018: 4th Congress on Robotics and Neuroscience","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.21428/5b03f636","is_oa":true,"landing_page_url":"https://doi.org/10.21428/5b03f636","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"CRoNe2018: 4th Congress on Robotics and Neuroscience","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1543217731","https://openalex.org/W1555405574","https://openalex.org/W1595605666","https://openalex.org/W1747702904","https://openalex.org/W2056161426","https://openalex.org/W2091875264","https://openalex.org/W2104641222","https://openalex.org/W2115288602","https://openalex.org/W2120346334","https://openalex.org/W2160308170","https://openalex.org/W2190033311","https://openalex.org/W2965916140","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347","https://openalex.org/W4210805261"],"abstract_inverted_index":{"Robotic":[0],"soccer":[1],"provides":[2],"an":[3],"adversarial":[4],"scenario":[5],"where":[6,59],"collaborative":[7],"agents":[8],"have":[9],"to":[10],"execute":[11],"actions":[12],"by":[13,32],"following":[14],"a":[15,18,33,56],"hand-coded":[16],"or":[17],"learned":[19],"strategy,":[20],"which":[21,51],"in":[22,83],"the":[23,26,46,66,69,72],"case":[24],"of":[25,40,65,68,71,85,87],"Small":[27],"Size":[28],"League,":[29],"is":[30,52,77],"given":[31],"centralized":[34,42],"decision":[35],"maker.This":[36],"work":[37],"takes":[38],"advantage":[39],"this":[41],"approach":[43],"for":[44,89],"modelling":[45],"keepaway":[47],"strategy":[48],"learning":[49,75,90],"problem":[50],"inherently":[53],"multi-agent,":[54],"as":[55],"single-agent":[57],"problem,":[58],"now":[60],"each":[61],"robot":[62],"forms":[63],"part":[64],"state":[67],"model.One":[70],"classical":[73],"reinforcement":[74],"methods":[76],"compared":[78],"with":[79],"its":[80],"batch":[81],"version":[82],"terms":[84],"amount":[86],"time":[88],"and":[91],"concluding":[92],"about":[93],"updates":[94],"efficiency":[95],"based":[96],"on":[97],"experiences":[98],"reusability.":[99]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}